Energy consumption determination method and device, electronic equipment and storage medium

Abstract

The invention relates to an energy consumption determination method and device, electronic equipment and a storage medium, and relates to the field of automobiles. The method comprises the steps of determining battery net energy consumption corresponding to each sub-time period in a plurality of sub-time periods included in a target time period according to driving data of a vehicle in the target time period; the battery net energy consumption is determined based on the energy consumed in the discharging process of the battery of the vehicle and the energy recycled through the energy recycling system, the battery net energy consumption corresponding to each sub-time period is corrected according to the battery net energy consumption corresponding to the multiple sub-time periods and the battery SOC variation, and the accuracy of energy consumption estimation can be improved.

Description

Technical Field

[0001] The present application relates to the automotive field, and specifically to an energy consumption determination method, device, electronic device and storage medium. Background Art

[0002] With the increasing shortage of fossil energy and the intensification of greenhouse gas emissions, the automotive industry is accelerating its transition to electrification. In this context, accurate acquisition of vehicle driving energy consumption data has become a core requirement in research fields such as energy-saving control strategy formulation, accurate estimation of driving range, and in-depth analysis of vehicle economy.

[0003] At present, the method for estimating the energy consumption of electric vehicles is mainly to estimate the energy consumption by calculating the product of the change in the battery state of charge (SOC) and the rated total electrical energy. The principle of this method is simple and easy to implement in engineering, but its estimation accuracy is highly dependent on the accuracy of the SOC data. Since there is an estimation error in the battery SOC itself, and rounding errors will also be generated during the storage of SOC data, the accuracy of energy consumption estimation will be affected. Especially for short driving segments with small SOC changes, the rounding error of SOC will be significantly amplified, resulting in a deviation between the energy consumption estimation result and the actual energy consumption value. Therefore, how to improve the accuracy of electric vehicle driving energy consumption estimation has become a technical problem that needs to be solved urgently. Summary of the invention

[0004] One of the purposes of the present invention is to provide an energy consumption determination method, device, electronic device and storage medium, which can improve the accuracy of energy consumption estimation.

[0005] In order to achieve the above object, the technical solution adopted by the present invention is as follows: According to a first aspect of the present invention, a method for determining energy consumption is provided, the method comprising: determining the battery net energy consumption corresponding to each of the multiple sub-time periods included in the target time period based on the driving data of the vehicle within the target time period; the battery net energy consumption is determined based on the energy consumed by the battery of the vehicle during the discharge process and the energy recovered by the energy recovery system. According to the battery net energy consumption corresponding to the multiple sub-time periods and the battery SOC change, the battery net energy consumption corresponding to each sub-time period is corrected.

[0006] According to the above technical means, the present application can determine the battery net energy consumption corresponding to each sub-time period based on the vehicle driving data related to the battery net energy consumption, so as to reduce the error introduced when directly using the battery SOC change to calculate the energy consumption, and also understand the energy consumption of the vehicle in different time periods. Afterwards, the battery net energy consumption corresponding to each sub-time period is corrected in combination with the battery SOC change corresponding to multiple sub-time periods. The corrected battery net energy consumption can more accurately reflect the actual battery consumption, thereby improving the accuracy and credibility of the energy consumption data.

[0007] In one possible method, the net battery energy consumption corresponding to each sub-time period is corrected according to the net battery energy consumption and the battery SOC change corresponding to the multiple sub-time periods, including: when the sum of the battery SOC changes corresponding to the multiple sub-time periods is greater than or equal to the SOC change sum threshold, the net battery energy consumption corresponding to each sub-time period is corrected according to the net battery energy consumption and the battery SOC change corresponding to the multiple sub-time periods.

[0008] According to the above technical means, the present application can correct the net energy consumption of the battery in each sub-time period when the battery SOC changes corresponding to multiple sub-time periods meet predetermined conditions, thereby improving the energy consumption correction efficiency.

[0009] In one possible manner, the driving data includes the nominal energy of the battery. On this basis, for any target sub-time period among the multiple sub-time periods, the net energy consumption of the battery corresponding to each sub-time period is corrected according to the net energy consumption of the battery and the change in battery SOC corresponding to the multiple sub-time periods, including: determining an energy consumption correction coefficient according to the nominal energy, the change in battery SOC corresponding to the multiple sub-time periods, and the net energy consumption of the battery. Based on the energy consumption correction coefficient, the net energy consumption of the battery corresponding to the target sub-time period is corrected.

[0010] According to the above technical means, this application determines the energy consumption correction coefficient by combining the nominal energy of the vehicle battery, the battery SOC changes corresponding to multiple sub-time periods, and the battery net energy consumption and other multi-dimensional information, which can comprehensively consider the actual performance of the battery under different working conditions, and use the energy consumption correction coefficient to correct the battery net energy consumption, so that the corrected battery net energy consumption can be more in line with the actual situation. In addition, by analyzing the corrected battery net energy consumption data, the corresponding power control strategy can be optimized, thereby improving energy utilization efficiency and reducing overall energy consumption.

[0011] In one possible manner, the energy consumption correction coefficient is determined according to the nominal energy, the battery SOC changes corresponding to the multiple sub-time periods, and the battery net energy consumption, including: determining the product of the nominal energy and the sum of the battery SOC changes corresponding to each sub-time period as the target product. The ratio of the target product to the sum of the battery net energy consumption corresponding to each sub-time period is determined as the energy consumption correction coefficient.

[0012] In a possible manner, for any target sub-time period among the multiple sub-time periods, the method further includes: selecting at least one first sub-time period from the multiple sub-time periods; the first sub-time period is adjacent to the target sub-time period, and the net battery energy consumption corresponding to the first sub-time period is not zero. On this basis, the net battery energy consumption corresponding to each sub-time period is corrected according to the net battery energy consumption and battery SOC change corresponding to the multiple sub-time periods, including: correcting the net battery energy consumption corresponding to the target sub-time period according to the net battery energy consumption and battery SOC change corresponding to at least one first sub-time period and the target sub-time period.

[0013] According to the above technical means, the present application can select the first sub-time period adjacent to the target sub-time period and with non-zero battery net energy consumption from multiple sub-time periods, so that a valid sub-time period related to the target sub-time period can be selected. Afterwards, by analyzing the adjacent sub-time periods with actual energy consumption changes, the changing trend of the battery net energy consumption in the target sub-time period can be more accurately understood, so as to more accurately correct the battery net energy consumption of the target sub-time period.

[0014] In one possible method, at least one first sub-time period is selected from multiple sub-time periods, including: taking the target sub-time period as the starting time period, adding the sub-time periods with non-zero battery net energy consumption to the first set one by one according to a preset time sequence, and adding the sub-time periods with zero battery net energy consumption to the second set until the preset filtering conditions are met.

[0015] According to the above technical means, the present application can sequentially traverse each sub-time period in a preset time sequence, which can ensure the consistency and integrity of the data. At the same time, it can also distinguish the battery net energy consumption status of the vehicle in different sub-time periods, and quickly filter out the sub-time periods adjacent to the target sub-time period and whose battery net energy consumption is not zero.

[0016] In one possible manner, the preset screening condition satisfies any one of the following items: the sum of the battery SOC changes corresponding to the first set is greater than or equal to the SOC change sum threshold; the sum of the battery output net energy consumption corresponding to the second set is greater than or equal to the battery output net energy consumption sum threshold, and the battery output net energy consumption is determined based on the battery status data corresponding to each sub-time period included in the second set and the cumulative mileage increase.

[0017] According to the above technical means, the present application can stop traversal and screening according to preset screening conditions, thereby reducing resource waste.

[0018] In one possible manner, the driving data includes a battery SOC change corresponding to each sub-time period. On this basis, the battery net energy consumption corresponding to each sub-time period within the target time period is determined according to the driving data of the vehicle within the target time period, including: for each sub-time period within the target time period, based on the battery SOC change corresponding to the sub-time period, the battery net energy consumption corresponding to the sub-time period is determined.

[0019] According to the above technical means, the present application can determine the battery net energy consumption corresponding to each sub-time period based on the battery SOC change corresponding to each sub-time period, and provide support for subsequent battery net energy consumption correction.

[0020] In one possible method, based on the battery SOC change corresponding to the sub-time period, the battery net energy consumption corresponding to the sub-time period is determined, including: when the battery SOC change corresponding to the sub-time period is less than the SOC change threshold, using a preset energy consumption estimation model to determine the battery net energy consumption corresponding to the sub-time period.

[0021] According to the above technical means, the present application can use the preset energy consumption estimation model to effectively handle the problem of estimating the battery net energy consumption when the battery SOC change is small, avoiding the problem of being unable to accurately determine the battery net energy consumption due to the insignificant battery SOC change. In addition, by determining the battery net energy consumption through the preset energy consumption estimation model, it is also possible to reduce the SOC estimation error and rounding error introduced when directly using the SOC change to calculate the energy consumption.

[0022] In one possible manner, the driving data also includes motor status data, battery status data, cumulative mileage increase, and driving time corresponding to each sub-time period. On this basis, when the battery SOC change corresponding to the sub-time period is less than the SOC change threshold, the preset energy consumption estimation model is used to determine the battery net energy consumption corresponding to the sub-time period, including: when the battery SOC change corresponding to the sub-time period is less than the SOC change threshold, based on the battery SOC change, cumulative mileage increase, driving time, motor status data, and battery status data corresponding to the sub-time period, the target energy consumption corresponding to the sub-time period is determined; the target energy consumption is other energy consumption except the battery net energy consumption. The target energy consumption and the driving data corresponding to the sub-time period are input into the preset energy consumption estimation model to obtain the battery net energy consumption corresponding to the sub-time period.

[0023] Based on the above-mentioned technical means, the present application can combine other energy consumption data related to the net energy consumption of the battery and multi-dimensional data information such as driving data to conduct a comprehensive analysis and calculation of the net energy consumption of the battery in the sub-time period, so as to obtain a net energy consumption value of the battery that is closer to the actual situation, thereby improving the accuracy of the energy consumption calculation.

[0024] In one possible manner, the driving data also includes the cumulative mileage increase, the battery status data and the nominal energy of the battery. On this basis, based on the battery SOC change corresponding to the sub-time period, the battery net energy consumption corresponding to the sub-time period is determined, including: when the battery SOC change corresponding to the sub-time period is greater than or equal to the SOC change threshold, based on the battery SOC change corresponding to the sub-time period, the cumulative mileage increase and the nominal energy of the power battery, the battery net energy consumption corresponding to the sub-time period is determined.

[0025] In one possible approach, the net battery energy consumption corresponding to the sub-time period satisfies the following formula: ; in, is the net energy consumption of the battery, is the battery SOC change, is the nominal energy, The amount added to the accumulated mileage.

[0026] According to the above technical means, the present application can quickly determine the battery net energy consumption corresponding to each sub-time period based on the battery net energy consumption calculation formula.

[0027] In one possible approach, each sub-time period contains multiple data frames, each data frame contains the driving data of the vehicle at a certain moment, and each sub-time period satisfies one or more of the following conditions: the time interval between any two adjacent data frames in the sub-time period is less than an interval threshold; the vehicles corresponding to any two adjacent data frames in the sub-time period are on the same road.

[0028] According to the above technical means, the present application can determine the driving segment to which the sub-time period belongs according to the time interval between any two adjacent data frames in the sub-time period, and / or the road where the vehicles corresponding to any two adjacent data frames are located, so as to realize the segment division of driving data.

[0029] According to a second aspect of the present invention, there is provided an energy consumption determination device, the device comprising: a determination unit and a processing unit.

[0030] A determination unit is used to determine the battery net energy consumption corresponding to each of the multiple sub-time periods included in the target time period based on the vehicle's driving data within the target time period; the battery net energy consumption is determined based on the energy consumed by the vehicle's battery during discharge and the energy recovered by the energy recovery system.

[0031] The processing unit is used to correct the battery net energy consumption corresponding to each sub-time period according to the battery net energy consumption and battery SOC changes corresponding to the multiple sub-time periods.

[0032] In one possible embodiment, the processing unit is also used to correct the battery net energy consumption corresponding to each sub-time period according to the battery net energy consumption corresponding to the multiple sub-time periods and the battery SOC changes, when the sum of the battery SOC changes corresponding to the multiple sub-time periods is greater than or equal to the SOC change sum threshold.

[0033] In one possible manner, the driving data includes the nominal energy of the battery. Based on this, for any target sub-time period in the multiple sub-time periods, the determination unit is further configured to determine the energy consumption correction coefficient according to the nominal energy, the battery SOC changes corresponding to the multiple sub-time periods, and the battery net energy consumption.

[0034] In a possible manner, the processing unit is further configured to correct the net energy consumption of the battery corresponding to the target sub-time period based on the energy consumption correction coefficient.

[0035] In one possible embodiment, the determination unit is also used to determine the product of the nominal energy and the sum of the battery SOC changes corresponding to each sub-time period as the target product, and determine the ratio of the target product to the sum of the battery net energy consumption corresponding to each sub-time period as the energy consumption correction coefficient.

[0036] In one possible manner, for any target sub-time period among multiple sub-time periods, the processing unit is also used to correct the battery net energy consumption corresponding to the target sub-time period based on the battery net energy consumption and battery SOC change corresponding to at least one first sub-time period and the target sub-time period.

[0037] In one possible manner, the driving data includes a battery SOC change corresponding to each sub-time period. On this basis, the determination unit is further configured to determine the battery net energy consumption corresponding to each sub-time period within the target time period based on the battery SOC change corresponding to the sub-time period.

[0038] In one possible manner, the determination unit is further configured to, when a battery SOC change corresponding to the sub-time period is less than an SOC change threshold, determine the battery net energy consumption corresponding to the sub-time period using a preset energy consumption estimation model.

[0039] In one possible manner, the driving data further includes motor status data, battery status data, cumulative mileage increase, and driving duration corresponding to each sub-time period. On this basis, the determination unit is further configured to determine the target energy consumption corresponding to the sub-time period based on the battery SOC change, cumulative mileage increase, driving duration, motor status data, and battery status data corresponding to the sub-time period when the battery SOC change corresponding to the sub-time period is less than the SOC change threshold.

[0040] In one possible manner, the driving data also includes the cumulative mileage increase, the battery status data and the nominal energy of the battery. On this basis, the determination unit is further used to determine the battery net energy consumption corresponding to the sub-time period based on the battery SOC change corresponding to the sub-time period, the cumulative mileage increase and the nominal energy of the power battery when the battery SOC change corresponding to the sub-time period is greater than or equal to the SOC change threshold.

[0041] According to a third aspect of the present invention, there is provided an electronic device, comprising: a processor; a memory for storing processor executable instructions; wherein the processor is configured to execute instructions to implement the method of the above-mentioned first aspect and any possible implementation manner thereof.

[0042] According to a fourth aspect provided by the present invention, a computer-readable storage medium is provided. When the instructions in the computer-readable storage medium are executed by a processor of a processing device, the processing device is enabled to execute the method in the above-mentioned first aspect and any possible implementation manner thereof.

[0043] According to a fifth aspect of the present invention, a computer program product is provided. The computer program product includes computer instructions. When the computer instructions are executed on a processing device, the processing device executes the method of the first aspect and any possible implementation manner thereof.

[0044] Therefore, the above technical features of the present invention have the following beneficial effects: (1) Based on the vehicle driving data related to the battery net energy consumption, the battery net energy consumption corresponding to each sub-time period can be determined. This can reduce the error introduced when directly using the battery SOC change to calculate the energy consumption, and can also understand the energy consumption of the vehicle in different time periods. Afterwards, the battery net energy consumption corresponding to each sub-time period is corrected based on the battery SOC change corresponding to multiple sub-time periods. The corrected battery net energy consumption can more accurately reflect the actual battery consumption, thereby improving the accuracy and credibility of the energy consumption data.

[0045] (2) When the battery SOC changes corresponding to the multiple sub-time periods meet the predetermined conditions, the battery net energy consumption in each sub-time period can be corrected, thereby improving the efficiency of energy consumption correction.

[0046] (3) By combining the nominal energy of the vehicle battery, the battery SOC changes corresponding to multiple sub-time periods, and the battery net energy consumption and other multi-dimensional information to determine the energy consumption correction coefficient, the actual performance of the battery under different working conditions can be comprehensively considered. The battery net energy consumption can be corrected using the energy consumption correction coefficient to make the corrected battery net energy consumption more consistent with the actual situation. In addition, by analyzing the corrected battery net energy consumption data, the corresponding power control strategy can be optimized, thereby improving energy utilization efficiency and reducing overall energy consumption.

[0047] (4) The first sub-time period adjacent to the target sub-time period and having a non-zero battery net energy consumption can be selected from multiple sub-time periods, so that a valid sub-time period related to the target sub-time period can be selected. Afterwards, by analyzing the adjacent sub-time periods with actual energy consumption changes, the changing trend of the battery net energy consumption within the target sub-time period can be more accurately understood, thereby more accurately correcting the battery net energy consumption of the target sub-time period.

[0048] (5) Each sub-time period can be traversed in sequence according to the preset time sequence, which can ensure the consistency and integrity of the data. At the same time, it can also distinguish the battery net energy consumption status of the vehicle in different sub-time periods, and quickly filter out the sub-time periods adjacent to the target sub-time period and with non-zero battery net energy consumption.

[0049] (6) You can stop traversal and filtering based on preset filtering conditions, thereby reducing resource waste.

[0050] (7) Based on the battery SOC change corresponding to each sub-time period, the battery net energy consumption corresponding to each sub-time period can be determined to provide support for subsequent battery net energy consumption correction.

[0051] (8) The preset energy consumption estimation model can be used to effectively handle the problem of estimating the battery net energy consumption when the battery SOC change is small, avoiding the problem of being unable to accurately determine the battery net energy consumption due to the insignificant battery SOC change. In addition, determining the battery net energy consumption through the preset energy consumption estimation model can also reduce the SOC estimation error and rounding error introduced when directly using the SOC change to calculate the energy consumption.

[0052] (9) The net energy consumption of the battery in each sub-time period can be comprehensively analyzed and calculated by combining other energy consumption data related to the net energy consumption of the battery and multi-dimensional data information such as driving data. This can obtain a net energy consumption value of the battery that is closer to the actual situation, thereby improving the accuracy of the energy consumption calculation.

[0053] (10) Based on the battery net energy consumption calculation formula, the battery net energy consumption corresponding to each sub-time period can be quickly determined.

[0054] (11) The driving segment to which the sub-time period belongs can be determined based on the time interval between any two adjacent data frames in the sub-time period and / or the road on which the vehicles corresponding to any two adjacent data frames are located, so as to realize segment division of the driving data. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 An architecture diagram of an energy consumption determination system provided in an embodiment of the present application; Figure 2 A schematic diagram of a flow chart of an energy consumption determination method provided in an embodiment of the present application; Figure 3 A flowchart of another method for determining energy consumption provided in an embodiment of the present application; Figure 4 A schematic diagram of a process for determining a preset energy consumption estimation model provided in an embodiment of the present application; Figure 5 A schematic diagram of a process for determining another preset energy consumption estimation model provided in an embodiment of the present application; Figure 6 A schematic diagram of the structure of an energy consumption determination device provided in an embodiment of the present application; Figure 7 A block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0056] In order to enable ordinary persons in the art to better understand the technical solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0057] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the attached claims.

[0058] In the embodiments of the present application, words such as "exemplary", "such as" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "exemplary", "such as" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "such as" or "for example" is intended to present related concepts in a concrete way.

[0059] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.

[0060] Figure 1 An architecture diagram of an energy consumption determination system provided in an embodiment of the present application, such as Figure 1 As shown, the system architecture includes: a server 101.

[0061] Among them, the server 101 can be a high-performance server that provides various services on the Internet, can be an independent physical server, can also be a server cluster composed of multiple physical servers, or can be at least one of the cloud servers that provide basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content distribution networks, and big data or artificial intelligence platforms, etc., which are not limited in the embodiments of the present application. Of course, the server can also include other functions to provide more comprehensive and diversified services.

[0062] The server 101 in the embodiment of the present application may be a single server, a server cluster, or a cloud server, which is not limited in the embodiment of the present application.

[0063] In the embodiment of the present application, the server 101 can determine the battery net energy consumption corresponding to each of the multiple sub-time periods included in the target time period based on the driving data of the vehicle in the target time period. Afterwards, the server can correct the battery net energy consumption corresponding to each sub-time period based on the battery net energy consumption corresponding to the multiple sub-time periods and the battery SOC change, so as to obtain a battery net energy consumption that is more in line with the actual situation.

[0064] The energy consumption determination system provided in the embodiment of the present application can be configured in a vehicle. The vehicle can also be called a vehicle, a mobile carrier, an electric vehicle (EV), a hybrid electric vehicle (HEV), a plug-in hybrid electric vehicle (PHEV), a fuel cell vehicle (FCV), an autonomous vehicle, an intelligent and connected vehicle (ICV), a driverless vehicle, etc.

[0065] In the embodiments of the present application, the vehicle may be a sedan, a sport utility vehicle (SUV), a truck, an electric vehicle, a motorcycle, a tricycle, a special vehicle (such as an ambulance, a fire truck, a police car, etc.), an unmanned taxi, an intelligent networked bus, an automatic driving logistics vehicle, an electric truck, etc. In addition, the method is also applicable to various special vehicles, such as agricultural vehicles, mining vehicles, forestry vehicles, airport vehicles, port vehicles, etc. This application does not impose specific restrictions on this.

[0066] For ease of understanding, the energy consumption determination method provided in this application is specifically introduced below with reference to the accompanying drawings.

[0067] Figure 2 A schematic diagram of a flow chart of an energy consumption determination method provided in an embodiment of the present application, such as Figure 2 As shown, this method is Figure 1 The server shown executes the method, comprising: S201. Determine, based on driving data of a vehicle within a target time period, a battery net energy consumption corresponding to each of a plurality of sub-time periods included in the target time period.

[0068] Among them, the net energy consumption of the battery is determined based on the energy consumed by the vehicle's battery during discharge and the energy recovered by the energy recovery system. The energy consumed by the battery during discharge refers to the energy released by the battery to drive the vehicle and maintain the operation of various systems of the vehicle during driving. The energy recovered by the energy recovery system refers to the energy that the drive motor can switch to generator mode during vehicle braking, deceleration or downhill, converting the vehicle's kinetic energy or gravitational potential energy into electrical energy and feeding it back to the battery.

[0069] In the embodiment of the present application, the battery net energy consumption may include the battery internal energy consumption and the battery output net energy consumption. The battery internal energy consumption refers to the energy loss caused by the physical and chemical characteristics of the battery during the charging and discharging process, mainly including internal resistance loss, chemical reaction loss, self-discharge loss, temperature-related loss, charge and discharge efficiency loss and battery aging loss. The battery output net energy consumption is the battery energy consumption excluding the battery internal energy consumption in the battery net energy consumption.

[0070] In the embodiment of the present application, as shown in Table 1, the driving data of the vehicle may include but is not limited to data collection time, drive motor speed, drive motor torque, motor controller input voltage, motor controller DC bus current, vehicle position (such as longitude, latitude), vehicle status, charging status, vehicle speed, cumulative mileage, total voltage, total current and SOC. For example, Table 1 shows a type of vehicle driving data collected based on the GB / T32960 standard, and each row may represent a data frame.

[0071] Table 1 Vehicle driving data

[0072] In one possible implementation, the server stores historical driving data of the vehicle. The server can filter out the vehicle driving data within a target time period from the historical driving data. Afterwards, the server can determine the battery net energy consumption corresponding to each sub-time period based on the vehicle driving data of each sub-time period included in the target time period.

[0073] Exemplarily, assuming that the three data frames in Table 1 belong to a sub-time period, the server can determine the battery net energy consumption corresponding to the sub-time period according to the multiple driving data included in the three data frames.

[0074] It should be noted that the net battery energy consumption corresponding to each sub-time period is the net battery energy consumption per unit mileage.

[0075] S202: According to the battery net energy consumption and battery SOC changes corresponding to the multiple sub-time periods, correct the battery net energy consumption corresponding to each sub-time period.

[0076] In one possible implementation, the server may determine the sum of the battery SOC changes corresponding to multiple sub-time periods within the target time period. When the sum of the battery SOC changes corresponding to the multiple sub-time periods is greater than or equal to the SOC change sum threshold, the server may correct the battery net energy consumption corresponding to each sub-time period according to the battery net energy consumption corresponding to the multiple sub-time periods and the battery SOC changes, and obtain the corrected battery net energy consumption.

[0077] In another possible implementation, when the sum of the battery SOC changes corresponding to multiple sub-time periods is less than the SOC change sum threshold, the server does not correct the battery net energy consumption corresponding to the sub-time periods in the multiple sub-time periods, that is, the server can determine the battery net energy consumption corresponding to each sub-time period obtained by the above S201 as the final battery net energy consumption.

[0078] Based on the above technical means, the server can determine the battery net energy consumption corresponding to each sub-time period based on multiple vehicle driving data related to the battery net energy consumption, which can effectively reduce the error introduced when only using the battery SOC change to calculate the energy consumption. In addition, when the sum of the battery SOC changes corresponding to multiple sub-time periods is greater than or equal to the SOC change sum threshold, the server can correct the battery net energy consumption corresponding to each sub-time period in combination with the battery SOC changes and battery net energy consumption corresponding to multiple sub-time periods, so that the corrected battery net energy consumption can more accurately reflect the actual battery energy consumption, thereby improving the accuracy and credibility of the energy consumption data, and can also screen out the sub-time periods that need to be corrected for the battery net energy consumption, reducing resource waste. At the same time, the battery net energy consumption determined by the above method includes the internal energy consumption of the battery, so that the battery energy consumption data can still maintain a high degree of accuracy under low temperature and battery aging conditions.

[0079] In some embodiments, the driving data may also include the nominal energy of the battery. On this basis, for any target sub-time period among the multiple sub-time periods, in the above S202, the net energy consumption of the battery corresponding to each sub-time period is corrected according to the net energy consumption of the battery and the change in battery SOC corresponding to the multiple sub-time periods, which may specifically include: the server may determine the energy consumption correction coefficient according to the nominal energy of the battery, the change in battery SOC corresponding to the multiple sub-time periods, and the net energy consumption of the battery. Afterwards, the server may correct the net energy consumption of the battery corresponding to the target sub-time period based on the energy consumption correction coefficient.

[0080] In the embodiment of the present application, the nominal energy of the battery refers to the total electrical energy that the battery of the vehicle can store or release under standard conditions, usually in kilowatt-hours (kWh).

[0081] In one possible implementation, the server may determine the product of the nominal energy and the sum of the battery SOC changes corresponding to each sub-time period as the target product. Afterwards, the server may determine the ratio of the target product to the sum of the battery net energy consumption corresponding to each sub-time period as the energy consumption correction coefficient. Finally, the server may use the product of the energy consumption correction coefficient and the battery net energy consumption corresponding to the target sub-time period as the corrected battery net energy consumption corresponding to the target sub-time period (hereinafter referred to as the target battery net energy consumption).

[0082] Exemplarily, the target sub-period The calculation formula of the corresponding target battery net energy consumption can refer to the following formula 1.

[0083] (Formula 1).

[0084] in, Target sub-time period The corresponding target battery net energy consumption, is the net battery energy consumption corresponding to the target sub-time period (net battery energy consumption per unit mileage), is the nominal energy, The target time period The battery SOC change corresponding to each sub-time period is: For the The net energy consumption per unit mileage corresponding to each sub-time period is: For the The cumulative mileage increase corresponding to each sub-time period is: For the The total battery net energy consumption corresponding to each sub-time period. , is an integer.

[0085] Based on the above technical means, this application determines the energy consumption correction coefficient by combining the nominal energy of the battery, the battery SOC change corresponding to multiple sub-time periods, the battery net energy consumption and other multi-dimensional information, so that the actual performance of the battery under different working conditions can be comprehensively considered. Afterwards, the net energy consumption of the battery is corrected using the energy consumption correction coefficient, so that the corrected net energy consumption of the battery can be more in line with the actual situation. In addition, by analyzing the corrected net energy consumption data of the battery, support can be provided for optimizing the power control strategy, thereby improving energy utilization efficiency and reducing overall energy consumption.

[0086] In some embodiments, for any target sub-time period among the multiple sub-time periods, in the above S202, the net battery energy consumption corresponding to each sub-time period is corrected according to the net battery energy consumption and battery SOC change corresponding to the multiple sub-time periods, which may specifically include: the server may select at least one first sub-time period from the multiple sub-time periods. Afterwards, the server may correct the net battery energy consumption corresponding to the target sub-time period according to the net battery energy consumption and battery SOC change corresponding to the at least one first sub-time period and the target sub-time period.

[0087] Among them, the first sub-time period is adjacent to the target sub-time period, and the net battery energy consumption corresponding to the first sub-time period is not zero. The first sub-time period is adjacent to the target sub-time period means that the start time of the first sub-time period can be adjacent to or close to the end time of the target sub-time period, or the end time of the first sub-time period can be adjacent to or close to the start time of the target sub-time period. The net battery energy consumption corresponding to the first sub-time period is not zero, which means that the net battery energy consumption corresponding to the first sub-time period can be a positive number or a negative number.

[0088] In a possible implementation, with the target sub-time period as the starting time period, the server can add the sub-time periods with non-zero battery net energy consumption in each sub-time period as the first sub-time period to the first set in a preset time sequence, and add the sub-time periods with zero battery net energy consumption to the second set until the preset screening condition is met. Afterwards, the server can correct the battery net energy consumption corresponding to the target sub-time period based on the battery net energy consumption corresponding to each first sub-time period in the first set and the target sub-time period and the battery SOC change, and obtain the target battery net energy consumption corresponding to the target sub-time period.

[0089] The preset screening condition satisfies any of the following: 1-1. The sum of battery SOC changes corresponding to the first set is greater than or equal to the SOC change sum threshold.

[0090] The SOC change amount sum threshold value may be determined according to actual needs. For example, the SOC change amount sum threshold value may be 6%, 10%, etc., and there is no limitation on this.

[0091] 1-2. The sum of the battery output net energy consumption corresponding to the second set is greater than or equal to the battery output net energy consumption sum threshold.

[0092] The battery output net energy consumption is determined based on the battery status data and the accumulated mileage increase corresponding to each sub-time period included in the second set. In the embodiment of the present application, the total battery output net energy consumption threshold can be determined according to actual needs. For example, the total battery output net energy consumption threshold can be 5%, 10% or 20%, or 0.5% or 0.6% of the nominal energy, etc., without limitation.

[0093] Optionally, the embodiment of the present application does not limit the preset time sequence. For example, with the target sub-time period as the starting time period, the server may first search the sub-time period before the target sub-time period, and then search the sub-time period after the target sub-time period, and so on, traversing each sub-time period one by one until the preset screening condition is met. Alternatively, the server may first search the sub-time period after the target sub-time period, and then search the sub-time period before the target sub-time period. That is, the server may filter out the first sub-time period from each sub-time period by alternating forward and backward searches.

[0094] In combination with the above embodiment, the method for correcting the battery net energy consumption corresponding to the target sub-time period is described in detail below by taking the preset time sequence of first searching forward and then searching backward as an example. Figure 3 As shown, the method includes: S301-S322.

[0095] S301: Parameter initialization.

[0096] For example, assuming that the target time period includes sub-time periods, namely {f1, f2, f3, ..., f n}, f n Indicates sub-time periods. Take the target sub-time period f i is the starting time period, let start=i, end=i, forward search flag backward=true, backward search flag forward=true, the first set and the second set are empty sets, and the battery output net energy consumption corresponding to the initial second set is .

[0097] S302, determine whether the forward search flag backward is true, if so, execute S303, if not, execute S314.

[0098] S303, determine sub-time period f start-1 Does it exist? If so, execute S304; if not, execute S314.

[0099] S304: Determine sub-time period f start-1 Whether the corresponding trusted battery net energy consumption is all zero, if so, execute S305, if not, execute S309.

[0100] In the embodiment of the present application, the credible battery net energy consumption corresponding to each sub-time period may include the battery net energy consumption obtained by a preset energy consumption estimation model (hereinafter referred to as ), the net battery energy consumption obtained by the preset energy consumption calculation formula (hereinafter referred to as ) and the target battery net energy consumption obtained by the above S202 (i.e., ).

[0101] It can be understood that, in the sub-time period f start-1 For example, in the sub-time period f start-1 When the corresponding battery net energy consumption is corrected, the corresponding credible battery net energy consumption may include and / or ,as well as , in the sub-time period f start-1 If the corresponding battery net energy consumption has not been corrected, the corresponding credible battery net energy consumption may include and / or .

[0102] Among them, the net battery energy consumption obtained by the preset energy consumption estimation model can refer to the introduction of the following embodiment, and the net battery energy consumption obtained by the preset energy consumption calculation formula can refer to the following formula 3, which will not be repeated here.

[0103] S305: Sub-time period f start-1 Join the second collection.

[0104] S306, determine whether the battery output net energy consumption corresponding to the second set is less than the total battery output net energy consumption threshold, if so, execute S307, if not, execute S308.

[0105] The battery output net energy consumption corresponding to the second set is the sum of the battery output net energy consumption corresponding to each sub-time period included in the set.

[0106] For example, suppose the sub-period f start-1 The corresponding total battery output net energy consumption is . Add sub-time segment f start-1 After that, the battery output net energy consumption corresponding to the second set is .in, The calculation formula can refer to the following formula 2.

[0107] (Formula 2).

[0108] in, is the sub-time period f start-1 The corresponding battery output net energy consumption per unit mileage is: is the sub-time period f start-1 The corresponding cumulative mileage increase.

[0109] S307. Let start=start-1.

[0110] S308, set the forward search flag backward=false.

[0111] S309, segment the sub-time start-1 Add the first set and set start=start-1.

[0112] S310, determine whether the sum of the battery SOC changes corresponding to the first set is greater than or equal to the SOC change sum threshold, or (backward | forward) = false, if so, execute S311, if not, execute S314.

[0113] Among them, | is an OR operation. For example, if either backward or forward is true, (backward | forward) = true; if both are false, (backward | forward) = false.

[0114] S311, determine whether the sum of the battery SOC changes corresponding to the first set is greater than or equal to the SOC change sum threshold, if so, execute S312, if not, execute S313.

[0115] S312: Based on the first set and the battery net energy consumption corresponding to the target sub-time period and the battery SOC change, correct the battery net energy consumption corresponding to the target sub-time period.

[0116] In the embodiment of the present application, the first set includes sub-time periods f start-1 For example, sub-time period f start-1 The corresponding battery net energy consumption can be obtained from its corresponding trusted battery net energy consumption , Select one from the list. The selection method can be random selection or selecting the one with the highest priority in order, such as has a higher priority than , has a higher priority than .

[0117] The server may refer to the above method to correct the net battery energy consumption corresponding to the target sub-time period, which will not be elaborated here.

[0118] S313: Taking the battery net energy consumption corresponding to the target sub-time period as the final battery net energy consumption.

[0119] S314, determine whether the backward search flag forward is true, if so, execute S315, if not, execute S302.

[0120] S315, determine sub-time period f end+1 Does it exist? If so, execute S316; if not, execute S302.

[0121] S316: Determine sub-time period f end+1 Whether the corresponding trusted battery net energy consumption is all zero, if so, execute S317, if not, execute S321.

[0122] Among them, the sub-time period f end+1 The corresponding trusted battery net energy consumption can refer to the introduction in the above S304, which will not be described in detail here.

[0123] S317: Sub-time period f end+1 Join the second collection.

[0124] S318, determine whether the battery output net energy consumption corresponding to the second set is less than the total battery output net energy consumption threshold, if so, execute S319, if not, execute S320.

[0125] S319. Let end=end+1.

[0126] S320, set the forward search flag forward=false.

[0127] S321, divide the sub-time into segments end+1 Add to the first set and set end=end+1.

[0128] S322, determine whether the sum of the battery SOC changes corresponding to the first set is greater than or equal to the SOC change sum threshold, or (backward | forward) = false, if so, execute S311, if not, execute S302.

[0129] Based on the above technical means, the present application can use the method of forward and backward alternating search to screen out the first sub-time period that is adjacent to the target sub-time period and valid from each sub-time period in turn. At the same time, a sub-time period skipping mechanism is added to allow a string of sub-time periods obtained by the search to be not strictly adjacent. Since the sum of the net energy consumption of the battery output corresponding to the skipped sub-time period (i.e., the sub-time period in the second set) is extremely small, the added error will also be extremely small, so the accuracy of the battery net energy consumption correction can be improved under the condition of slightly ignoring some errors, thereby improving the accuracy of the final battery energy consumption.

[0130] The above-mentioned embodiments introduce methods for correcting the net battery energy consumption corresponding to the target sub-time period. The following will introduce how to determine the net battery energy consumption corresponding to each sub-time period within the target time period in the embodiments of the present application.

[0131] In some embodiments, in the above S201, the net battery energy consumption corresponding to each sub-time period within the target time period is determined based on the driving data of the vehicle within the target time period, which may include: for each sub-time period within the target time period, the server can determine the net battery energy consumption corresponding to the sub-time period based on the battery SOC change corresponding to the sub-time period.

[0132] In one possible implementation, for each sub-time period within the target time period, when the battery SOC change corresponding to the sub-time period is greater than or equal to the SOC change threshold, the server can determine the battery net energy consumption corresponding to the sub-time period based on the battery SOC change corresponding to the sub-time period, the cumulative mileage increase and the nominal energy of the power battery.

[0133] In the embodiment of the present application, the SOC change threshold can be set according to actual needs. For example, the SOC change threshold can be 4%, 5%, etc., which is not limited.

[0134] Specifically, the server may use the product of the battery SOC change corresponding to the sub-time period and the nominal energy as the target parameter. Afterwards, the server may determine the ratio of the target parameter to the cumulative mileage increase corresponding to the sub-time period as the battery net energy consumption corresponding to the sub-time period (i.e., the net energy consumption in S304 above). ).

[0135] Exemplarily, the calculation formula for the net battery energy consumption corresponding to the sub-time period may refer to the following formula 3.

[0136] (Formula 3).

[0137] in, is the net battery energy consumption corresponding to the sub-time period (i.e., the net battery energy consumption per unit mileage), is the battery SOC change corresponding to the sub-time period, is the nominal energy, is the cumulative mileage increase corresponding to the sub-time period.

[0138] In another possible implementation, a preset energy consumption estimation model is deployed in the server. Based on this, for each sub-time period within the target time period, when the battery SOC change corresponding to the sub-time period is less than the SOC change threshold, the server can use the preset energy consumption estimation model to determine the battery net energy consumption corresponding to the sub-time period.

[0139] Specifically, the driving data within the target time period may include motor status data, battery status data, cumulative mileage increase, and driving time corresponding to each sub-time period. On this basis, for each sub-time period within the target time period, the server may determine the target energy consumption corresponding to the sub-time period based on the battery SOC change, cumulative mileage increase, driving time, motor status data, and battery status data corresponding to the sub-time period. Afterwards, the server may input the target energy consumption and the driving data corresponding to the sub-time period into a preset energy consumption estimation model to obtain the battery net energy consumption corresponding to the sub-time period (i.e., the net energy consumption of the battery in S304 above). ).

[0140] The target energy consumption is other energy consumption except the battery net energy consumption. In the embodiment of the present application, the target energy consumption may include but is not limited to the battery output net energy consumption, the battery internal energy consumption, the motor net energy consumption, other accessory energy consumption and regenerative braking recovery energy. The calculation formula can refer to the following formula 4. Battery internal energy consumption The calculation formula can refer to the following formula 5. The net energy consumption of the motor The calculation formula can refer to the following formula 6. Other accessories energy consumption The calculation formula can refer to the following formula 7, regenerative braking recovery energy The calculation formula can refer to the following formula 8.

[0141] (Formula 4).

[0142] (Formula 5).

[0143] (Formula 6).

[0144] (Formula 7).

[0145] (Formula 8).

[0146] in, is the total battery voltage corresponding to time t in the sub-time period, is the total battery current corresponding to time t in the sub-time period, is the motor controller input voltage corresponding to time t in the sub-time period, is the DC bus current of the motor controller corresponding to time t in the sub-time period, is the cumulative mileage increase corresponding to the sub-time period, is the driving time corresponding to the sub-time period.

[0147] Based on the above technical means, when the battery SOC change is small, the use of a preset energy consumption estimation model can reduce the error caused by the battery SOC change. When the battery SOC change is large, the accuracy of the battery net energy consumption obtained by using the preset energy consumption calculation formula can meet actual needs. In this way, by selecting different battery net energy consumption determination strategies based on the battery SOC change, it can adapt to the characteristics of the battery under different working conditions, and flexibly select appropriate methods to determine the battery net energy consumption to ensure the accuracy of the battery energy consumption estimation. The adaptability of the entire energy consumption estimation system is improved.

[0148] In some embodiments, Figure 4 As shown, the above preset energy consumption estimation model can be obtained through the following S401-S407.

[0149] S401: Preprocess the vehicle's driving data.

[0150] Specifically, the server stores the driving data of the vehicle. The server can integrate the driving data into structured data with the acquisition time series as rows and various operating parameters as columns. Each row in the structured data is a data frame, and each data frame contains the driving data of the vehicle at a certain moment. The specific format is shown in Table 1 above. Afterwards, the server can process the abnormal values ​​and missing values ​​in the driving data to obtain high-quality driving data.

[0151] For example, each operating parameter corresponds to a threshold range, and each threshold range is determined based on the specifications of the vehicle and its components. Taking the drive motor speed as an example, if the drive motor speed in a data frame exceeds the drive motor speed threshold range (between -5000rpm and 13000rpm), the drive motor speed of the data frame is replaced with the missing value. After that, the server can use the preset interpolation algorithm to process the missing value to obtain the interpolation value, and fill the interpolation value into the corresponding missing value.

[0152] In the embodiment of the present application, the interpolation algorithm may include a regression interpolation algorithm, a multiple interpolation algorithm, a linear interpolation algorithm, or a nearest neighbor interpolation algorithm, etc., without limitation. For example, in the case where parameters such as vehicle speed and total current are missing values, a regression interpolation algorithm or a multiple interpolation algorithm may be used for interpolation processing. For parameters such as cumulative mileage and SOC, a linear interpolation algorithm or a nearest neighbor interpolation algorithm may be used for interpolation processing.

[0153] S402: Acquire driving data of the vehicle in multiple sub-time periods.

[0154] Each sub-time period may satisfy one or more of the following conditions: 2-1. The time interval between any two adjacent data frames in the sub-time period is less than the interval threshold.

[0155] In the embodiment of the present application, the interval threshold can be determined according to actual needs, such as 500 seconds, 600 seconds, etc., which is not limited.

[0156] 2-2. The vehicles corresponding to any two adjacent data frames in the sub-time period are on the same road.

[0157] Specifically, the server may divide the data frames in the driving data according to a preset division rule to obtain the driving data in each sub-time period.

[0158] The preset division rules may include division according to time intervals and division according to roads, etc., which are not limited.

[0159] Take the division by time interval as an example. The server can traverse each data frame in the driving data. If the time interval between the first data frame and the second data frame is less than or equal to the interval threshold, the first data frame and the second data frame belong to the same sub-time period (i.e., the same driving segment). If the time interval between the first data frame and the second data frame is greater than the interval threshold, the first data frame is divided into the first sub-time period, and the second data frame is divided into the second sub-time period.

[0160] Take the division by road as an example. If the road where the vehicle corresponding to the second data frame is located is the same as the road where the vehicle corresponding to the first data frame is located, then the first data frame and the second data frame belong to the same sub-time period. If the road where the vehicle corresponding to the second data frame is located is different from the road where the vehicle corresponding to the first data frame is located, then the first data frame is divided into the last data frame of the first sub-time period, and into the starting frame of the second sub-time period, and the second data frame is divided into the starting frame of the second sub-time period. That is, the first sub-time period and the second sub-time period both contain the first data frame, and in the embodiment of the present application, the sub-time period containing the common data frame is determined as an adjacent sub-time period.

[0161] S403: Determine the battery net energy consumption, target energy consumption and energy consumption influencing parameters corresponding to each sub-time period based on the driving data corresponding to each sub-time period.

[0162] Specifically, the calculation formula of the battery net energy consumption can refer to the above formula 3, and the calculation formula of the target energy consumption can refer to the above formula 4-formula 8, which will not be repeated here. For the battery net energy consumption, as well as the battery output net energy consumption, motor net energy consumption and regenerative braking recovery energy in the target energy consumption, the following explanation is made: (1) The calculation of battery output net energy consumption, motor net energy consumption and regenerative braking recovery energy is realized based on complex numerical integration. There may be a large time interval between the data frames in the sub-time period, which is likely to cause a significant decrease in the integration accuracy and lead to inaccurate calculated results. In addition, when the number of data frames contained in the sub-time period is less than the number threshold, the integration accuracy is low. Therefore, for the sub-time period where the maximum time interval of the data frame is higher than the predetermined threshold (such as 30 seconds) or the number of data frames is less than the number threshold (such as 21), it is considered that the numerical integration is not feasible. Therefore, the motor net energy consumption and regenerative braking recovery energy corresponding to the sub-time period are set to missing values, but the corresponding battery output net energy consumption is still calculated.

[0163] (2) If the battery SOC change corresponding to a sub-time period is less than the SOC change threshold, the battery net energy consumption corresponding to the sub-time period is set to the missing value.

[0164] In the embodiment of the present application, the energy consumption influencing parameter refers to a parameter that is directly or indirectly related to the net energy consumption of the battery, as shown in Table 2. It is an energy consumption influencing parameter determined based on the driving data corresponding to each sub-time period and the ground meteorological data, and mainly includes five categories: kinematic parameters, time parameters, battery status data, motor status data, and meteorological data. The sub-parameters contained in each category of data can be referred to the introduction in Table 2.

[0165] Table 2 Parameters affecting energy consumption

[0166] It should be noted that after the vehicle's driving data is preprocessed in the above S401, there may still be invisible outliers in the driving data, which is specifically manifested in that a certain operating parameter in the driving data may be within the threshold range, but the direction or rate of change of the operating parameter along the time axis is contrary to common sense. For example, the cumulative mileage corresponding to the sub-time period should be a monotonically increasing sequence, but the cumulative mileage corresponding to some sub-time periods has decreased. For another example, the battery SOC change corresponding to the sub-time period during driving should decrease, that is, it is in an energy consumption state, but the battery SOC change corresponding to some sub-time periods is an increment. For another example, the internal energy consumption of the battery corresponding to the sub-time period is greater than the energy consumption threshold, and the sub-time period is regarded as an abnormal sub-time period.

[0167] Based on the above content, after the server determines the battery net energy consumption, target energy consumption and energy consumption influencing parameters corresponding to each sub-time period, the sub-time period in which the driving data, battery net energy consumption and target energy consumption have abnormal conditions can be deleted to obtain higher quality training data to train the energy consumption estimation model, so as to ensure the estimation accuracy of the energy consumption estimation model.

[0168] For example, the server may delete the sub-time period when the battery SOC change is less than -1%. For another example, the server may delete the sub-time period when the average speed is less than 0. For another example, for each target energy consumption, the server may count the high predetermined percentile (such as 99.7%) and the low predetermined percentile (such as 0.3%) of the target energy consumption, and then the server may delete the sub-time period when the target energy consumption is not between the high predetermined percentile and the low predetermined percentile.

[0169] S404: Determine a training set from multiple sub-time periods.

[0170] Specifically, for each of the multiple sub-time periods, the server can filter out data frames with non-empty battery net energy consumption from the sub-time period. Afterwards, the server can randomly shuffle the multiple sub-time periods and divide them into a training data set and a test data set based on a preset ratio.

[0171] The training set is used to train the energy consumption estimation model, and the test set is used to evaluate the generalization ability of the trained energy consumption estimation model, that is, the actual performance of the model on unknown data (that is, the test set).

[0172] The embodiment of the present application does not limit the preset ratio. For example, the data frame is divided into a training set and a test set at a ratio of 5:1, or the data frame is divided into a training set and a test set at a ratio of 3:1.

[0173] S405 , selecting optimal features from the training set including the driving data, target energy consumption and energy consumption influencing parameters corresponding to each sub-time period as input features of the energy consumption estimation model.

[0174] In the embodiments of the present application, the optimal features can be screened out using methods such as manual feature selection and backward sequence feature elimination.

[0175] In one example, taking the battery net energy consumption (also called battery SOC energy consumption) as the variable predicted by the energy consumption estimation model, and the target energy consumption and the energy consumption influencing parameters shown in Table 2 as the input features of the energy consumption estimation model, the artificial feature selection method can be used to delete any two features of the segment start time (i.e., the start time of the sub-time period), the segment end time (i.e., the end time of the sub-time period), and the segment battery SOC change, because the tendency of these three features to the battery net energy consumption is indirectly achieved by changing the traffic and weather conditions, and is relatively redundant in the case of kinematic parameter features and meteorological data features, that is, only one feature can be retained. Afterwards, in order to avoid errors in the output of the battery net energy consumption due to estimation errors and rounding errors in the training data during the training process, or the inability to output the predicted battery net energy consumption due to the lack of internal battery energy consumption, the internal battery energy consumption and the segment duration (i.e., the duration of the sub-time period) can also be deleted. After deleting some features by artificial feature selection based on empirical knowledge, the backward sequence feature elimination method can also be used to obtain the optimal feature set. The specific selection method can refer to the following. Figure 5 The illustrated embodiments are not described in detail here.

[0176] S406. Optimize hyperparameters of the energy consumption estimation model.

[0177] Among them, hyperparameters refer to parameters set before training the model to control the behavior and performance of the model. The choice of hyperparameters can affect the training speed, convergence, capacity and generalization ability of the model.

[0178] Specifically, the server may first determine the target hyperparameter and the search range corresponding to each target hyperparameter, and then determine the optimal value of each hyperparameter from the search range corresponding to each target hyperparameter using a preset hyperparameter optimization algorithm.

[0179] For example, Table 3 shows the search range of each hyperparameter, where the target hyperparameters may include the number of iterations (n_estimators), the number of leaf nodes in each tree (num_leaves), the maximum depth of the tree (max_depth), the learning rate (learning_rate), the minimum number of samples required for leaf nodes (min_child_samples), the sample ratio used when training each tree (subsample), the subsample frequency, i.e., how many iterations are repeated for subsampling (subsample_freq), the feature subsampling ratio (colsample_bytree), the feature subsampling ratio (colsample_bytree), etc., without limitation.

[0180] Table 3 Target hyperparameters and the search range of each hyperparameter

[0181] In the embodiment of the present application, the preset hyperparameter optimization algorithm may include a random search algorithm, a Bayesian optimization algorithm, a grid search algorithm, etc., without limitation.

[0182] In the embodiment of the present application, the energy consumption estimation model may include a LightGBM model, an XGBoost model, a random forest model, etc., without limitation.

[0183] For example, the energy consumption estimation model is the LightGBM model, and the preset hyperparameter optimization algorithm is the Bayesian optimization algorithm. The server can use the Python language to call the lightgbm package to implement the LightGBM model, that is, the energy consumption estimation model. After that, the server can call the Bayesian optimization algorithm (tree-structured parzenestimator, TPE) provided by the optuna package to search for the optimal hyperparameters of the energy consumption estimation model. In the process of searching for hyperparameters, the accuracy index of each set of hyperparameters can be obtained using the K-fold cross-validation method, and the accuracy index can be the root mean square error RMSE.

[0184] S407: Based on the optimized hyperparameters and the training set containing the optimal features, train the energy consumption estimation model to obtain a trained energy consumption estimation model.

[0185] Specifically, the server may set the hyperparameters of the energy consumption estimation model to optimized hyperparameters in advance. Afterwards, the server may input the training set containing the optimal features into the energy consumption estimation model to obtain the trained energy consumption estimation model.

[0186] Based on the above technical means, the manual feature selection method and the backward sequence feature elimination method can be used to determine the optimal input features and delete redundant features to ensure the accuracy of the energy consumption estimation model. Afterwards, the energy consumption estimation model is trained using the optimal features and optimized hyperparameters to provide support for the calculation of the battery's net energy consumption. At the same time, the battery net energy consumption output by the energy consumption estimation model trained based on a large amount of data is more accurate and can better reflect the actual energy consumption.

[0187] In some embodiments, Figure 5 As shown, the optimal features are determined using the backward sequence feature elimination method. For details, please refer to the following steps 1 to 9.

[0188] Step 1: Obtain a sub-training set from the training set for optimal feature selection.

[0189] It should be noted that the feature selection method based on backward sequence feature elimination has a large amount of computation, so the server can extract a sub-training set for optimal feature selection from the training set by random sampling. The sample size of the sub-training set can be determined according to actual computing resources and is not limited to this.

[0190] Step 2: Use the sub-training set to train the energy consumption estimation model and determine the initial accuracy index of the energy consumption estimation model.

[0191] In the embodiment of the present application, the accuracy index may include root mean square error (RMSE), mean square error (MSE), etc., without limitation.

[0192] Specifically, the server can input other features in the sub-training set except the battery net energy consumption feature into the energy consumption estimation model to obtain the battery net energy consumption output by the model. Afterwards, the server can calculate the accuracy index of the energy consumption estimation model based on the battery net energy consumption corresponding to each sub-time period in the sub-training set and the battery net energy consumption output by the model.

[0193] Step 3: Initialize the feature sequence i=1 in the sub-training set.

[0194] Step 4: Determine whether i is greater than the number of remaining features i in the sub-training set _ max, if yes, go to step 7, if no, go to step 5.

[0195] Step 5: Use the features other than the i-th feature in the sub-training set to train the energy consumption estimation model, and determine the accuracy index corresponding to the energy consumption estimation model.

[0196] Step 6: Let i=i+1.

[0197] Step 7: Determine the target feature so that the energy consumption estimation model trained based on features other than the target feature has the highest accuracy index, and delete the target feature in the sub-training set.

[0198] Step 8: Determine the number of remaining features i _ max=1 or whether the number of consecutive decreases of the accuracy index of the energy consumption estimation model is greater than the number threshold, if so, execute step 9, if not, execute step 3.

[0199] The number threshold may be 5 times, 6 times, etc., and this application does not limit this.

[0200] Step 9: The input features corresponding to the energy consumption estimation model with the highest accuracy index are used as the optimal features of the sub-training set.

[0201] In combination with the above steps 1 to 9, it can be understood that multiple rounds of iterations can be performed using backward sequence feature elimination. By deleting a feature in the sub-training in each round of iteration, the original features in the sub-training set are streamlined to the optimal features to improve the accuracy of the energy consumption estimation model. The optimal feature finally obtained is the input feature corresponding to the model with the highest accuracy index in all iterations.

[0202] In the embodiment of the present application, the optimal features may vary depending on the training set. For example, the optimal features may include the start SOC of the segment, the cumulative mileage at the start of the segment, the net energy consumption of the battery output, the energy consumption of other accessories, the mean torque of the generator motor, the standard deviation of the torque of the power-consuming motor, the standard deviation of the torque of the generator motor, the proportion of the torque of the power-consuming motor, the proportion of the torque of the generator motor, the average temperature of the motor, the energy recovered by regenerative braking, the average speed, the standard deviation of the non-zero speed, the 5% quantile of the non-zero speed, the kurtosis of the non-zero speed, the skewness of the non-zero speed, the absolute cumulative change of the speed, the average temperature, the average relative humidity, etc.

[0203] Figure 6 A schematic diagram of the structure of an energy consumption determination device provided in an embodiment of the present application is shown in FIG. Figure 6 As shown, the device includes: a determining unit 601 and a processing unit 602.

[0204] The determination unit 601 is used to determine the battery net energy consumption corresponding to each of the multiple sub-time periods included in the target time period according to the driving data of the vehicle in the target time period.

[0205] The processing unit 602 is used to correct the battery net energy consumption corresponding to each sub-time period according to the battery net energy consumption and battery SOC changes corresponding to the multiple sub-time periods.

[0206] In one possible embodiment, the processing unit 602 is also used to correct the battery net energy consumption corresponding to each sub-time period according to the battery net energy consumption corresponding to the multiple sub-time periods and the battery SOC changes, when the sum of the battery SOC changes corresponding to the multiple sub-time periods is greater than or equal to the SOC change sum threshold.

[0207] In one possible manner, the driving data includes the nominal energy of the battery. On this basis, for any target sub-time period in the multiple sub-time periods, the determination unit 601 is further used to determine the energy consumption correction coefficient according to the nominal energy, the battery SOC changes corresponding to the multiple sub-time periods, and the battery net energy consumption.

[0208] In a possible manner, the processing unit 602 is further configured to correct the net battery energy consumption corresponding to the target sub-time period based on the energy consumption correction coefficient.

[0209] In one possible manner, the determination unit 601 is also used to determine the product of the nominal energy and the sum of the battery SOC changes corresponding to each sub-time period as the target product, and to determine the ratio of the target product to the sum of the battery net energy consumption corresponding to each sub-time period as the energy consumption correction coefficient.

[0210] In one possible manner, for any target sub-time period among multiple sub-time periods, the processing unit 602 is also used to correct the battery net energy consumption corresponding to the target sub-time period based on the battery net energy consumption and battery SOC change corresponding to at least one first sub-time period and the target sub-time period.

[0211] In one possible manner, the driving data includes the battery SOC change corresponding to each sub-time period. On this basis, the determination unit 601 is further used to determine the battery net energy consumption corresponding to each sub-time period within the target time period based on the battery SOC change corresponding to the sub-time period.

[0212] In one possible manner, the determination unit 601 is further configured to, when a battery SOC change corresponding to a sub-time period is less than an SOC change threshold, determine the battery net energy consumption corresponding to the sub-time period using a preset energy consumption estimation model.

[0213] In one possible manner, the driving data further includes motor status data, battery status data, cumulative mileage increase, and driving duration corresponding to each sub-time period. On this basis, the determination unit 601 is further used to determine the target energy consumption corresponding to the sub-time period based on the battery SOC change, cumulative mileage increase, driving duration, motor status data, and battery status data corresponding to the sub-time period when the battery SOC change corresponding to the sub-time period is less than the SOC change threshold.

[0214] In one possible manner, the driving data also includes the cumulative mileage increase, the battery status data and the nominal energy of the battery. On this basis, the determination unit 601 is further used to determine the battery net energy consumption corresponding to the sub-time period based on the battery SOC change corresponding to the sub-time period, the cumulative mileage increase and the nominal energy of the power battery when the battery SOC change corresponding to the sub-time period is greater than or equal to the SOC change threshold.

[0215] Figure 7 A block diagram of an electronic device provided in an embodiment of the present application. Figure 7 As shown, the electronic device includes but is not limited to: a processor 701 and a memory 702 .

[0216] The memory 702 is used to store executable instructions of the processor 701. It can be understood that the processor 701 is configured to execute instructions to implement the vehicle control method in the above embodiment.

[0217] It should be noted that those skilled in the art can understand that Figure 7 The electronic device structure shown in the figure does not constitute a limitation on the electronic device, and the electronic device may include Figure 7 More or fewer components may be shown, or certain components may be combined, or the components may be arranged differently.

[0218] The processor 701 is the control center of the electronic device. It uses various interfaces and lines to connect various parts of the entire electronic device. By running or executing software programs and / or modules stored in the memory 702, and calling data stored in the memory 702, it performs various functions of the electronic device and processes data, thereby monitoring the electronic device as a whole. The processor 701 may include one or more processing units. Optionally, the processor 701 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 701.

[0219] The memory 702 may be used to store software programs and various data. The memory 702 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required by at least one functional module (such as a determination unit, a processing unit, etc.), etc. In addition, the memory 702 may include a high-speed random access memory, and may also include a non-volatile memory. For example, the non-volatile memory may include at least one disk storage device, a flash memory device, or other non-volatile solid-state storage devices.

[0220] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided, such as a memory 702 including instructions. The above instructions can be executed by a processor 701 of an electronic device to implement the method in the above embodiment.

[0221] In actual implementation, Figure 6 The functions of the determination unit 601 and the processing unit 602 in Figure 7 The processor 701 in the embodiment calls the computer program stored in the memory 702. The specific execution process can refer to the description of the method part in the above embodiment, which will not be repeated here.

[0222] Optionally, the computer-readable storage medium may be a non-temporary computer-readable storage medium, for example, the non-temporary computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0223] In an exemplary embodiment, the present application also provides a computer program product including one or more instructions, and the one or more instructions can be executed by the processor 701 of the electronic device to complete the method in the above embodiment.

[0224] It should be noted that when the instructions in the above-mentioned computer-readable storage medium or one or more instructions in the computer program product are executed by the processor of the electronic device, the various processes of the above-mentioned method embodiment are implemented, and the same technical effect as the above-mentioned method can be achieved. To avoid repetition, they will not be repeated here.

[0225] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0226] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0227] The units described as separate components may or may not be physically separated, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0228] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0229] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to execute all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, ROM, RAM, disk or CD and other media that can store program code.

[0230] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto, and any changes or substitutions within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for determining energy consumption, characterized in that: The method comprises: Determine, according to the driving data of the vehicle in the target time period, the net energy consumption of the battery corresponding to each of the multiple sub-time periods included in the target time period; the net energy consumption of the battery is determined based on the energy consumed by the battery of the vehicle during the discharge process and the energy recovered by the energy recovery system; The net energy consumption of the battery corresponding to each sub-time period is corrected according to the net energy consumption of the battery and the battery SOC change corresponding to the multiple sub-time periods.

2. The method according to claim 1, characterized in that The correcting the battery net energy consumption corresponding to each sub-time period according to the battery net energy consumption and the battery SOC change corresponding to the multiple sub-time periods includes: When the sum of the battery SOC changes corresponding to the multiple sub-time periods is greater than or equal to the SOC change sum threshold, the battery net energy consumption corresponding to each sub-time period is corrected according to the battery net energy consumption corresponding to the multiple sub-time periods and the battery SOC changes.

3. The method according to claim 2, characterized in that The driving data includes the nominal energy of the battery; for any target sub-time period in the multiple sub-time periods, The correcting the battery net energy consumption corresponding to each sub-time period according to the battery net energy consumption and the battery SOC change corresponding to the multiple sub-time periods includes: Determining an energy consumption correction coefficient according to the nominal energy, the battery SOC changes corresponding to the multiple sub-time periods, and the battery net energy consumption; Based on the energy consumption correction coefficient, the net energy consumption of the battery corresponding to the target sub-time period is corrected.

4. The method according to claim 3, characterized in that The determining of the energy consumption correction coefficient according to the nominal energy, the battery SOC changes corresponding to the multiple sub-time periods, and the battery net energy consumption includes: Determine the product of the nominal energy and the sum of the battery SOC changes corresponding to each sub-time period as a target product; The ratio of the target product to the sum of the net energy consumption of the battery corresponding to each sub-time period is determined as the energy consumption correction coefficient.

5. The method according to any one of claims 1 to 4, characterized in that For any target sub-time period among the multiple sub-time periods, the method further includes: Selecting at least one first sub-time period from the multiple sub-time periods; the first sub-time period is adjacent to the target sub-time period, and the net battery energy consumption corresponding to the first sub-time period is not zero; The correcting the battery net energy consumption corresponding to each sub-time period according to the battery net energy consumption and the battery SOC change corresponding to the multiple sub-time periods includes: According to the battery net energy consumption corresponding to the at least one first sub-time period and the target sub-time period and the battery SOC change, the battery net energy consumption corresponding to the target sub-time period is corrected.

6. The method according to claim 5, characterized in that The step of selecting at least one first sub-time period from the plurality of sub-time periods comprises: Taking the target sub-time period as the starting time period, the sub-time periods with non-zero battery net energy consumption are added to the first set one by one in a preset time sequence, and the sub-time periods with zero battery net energy consumption are added to the second set until the preset screening condition is met.

7. The method according to claim 6, characterized in that The preset screening condition meets any of the following conditions: The sum of the battery SOC changes corresponding to the first set is greater than or equal to the SOC change sum threshold; The sum of the battery output net energy consumption corresponding to the second set is greater than or equal to a battery output net energy consumption sum threshold; The battery output net energy consumption is determined based on the battery status data corresponding to each sub-time period included in the second set and the accumulated mileage increase.

8. The method according to claim 1, characterized in that The driving data includes a battery SOC change corresponding to each sub-time period; The determining, based on the driving data of the vehicle within the target time period, the battery net energy consumption corresponding to each sub-time period within the target time period includes: For each sub-time period within the target time period, the battery net energy consumption corresponding to the sub-time period is determined based on the battery SOC change corresponding to the sub-time period.

9. The method according to claim 8, characterized in that The determining the battery net energy consumption corresponding to the sub-time period based on the battery SOC change corresponding to the sub-time period includes: When the battery SOC change corresponding to the sub-time period is less than the SOC change threshold, the battery net energy consumption corresponding to the sub-time period is determined by using a preset energy consumption estimation model.

10. The method according to claim 9, characterized in that The driving data also includes motor status data, battery status data, cumulative mileage increase and driving time corresponding to each sub-time period; When the battery SOC change amount corresponding to the sub-time period is less than the SOC change amount threshold, determining the battery net energy consumption corresponding to the sub-time period by using a preset energy consumption estimation model includes: When the battery SOC change corresponding to the sub-time period is less than the SOC change threshold, the target energy consumption corresponding to the sub-time period is determined based on the battery SOC change corresponding to the sub-time period, the accumulated mileage increase, the driving time, the motor state data and the battery state data; the target energy consumption is other energy consumption except the battery net energy consumption; The target energy consumption and the driving data corresponding to the sub-time period are input into the preset energy consumption estimation model to obtain the battery net energy consumption corresponding to the sub-time period.

11. The method according to claim 8, characterized in that The driving data also includes the cumulative mileage increase, battery status data and the nominal energy of the battery; The determining the battery net energy consumption corresponding to the sub-time period based on the battery SOC change corresponding to the sub-time period includes: When the battery SOC change corresponding to the sub-time period is greater than or equal to the SOC change threshold, the battery net energy consumption corresponding to the sub-time period is determined based on the battery SOC change corresponding to the sub-time period, the accumulated mileage increase and the nominal energy of the power battery.

12. The method according to claim 11, characterized in that The net energy consumption of the battery corresponding to the sub-time period satisfies the following formula: ； Among them, the is the net energy consumption of the battery, is the battery SOC change, is the nominal energy, The amount of increase in the accumulated mileage.

13. The method according to claim 1, characterized in that Each sub-time period contains multiple data frames, each of which contains the driving data of the vehicle at a certain moment. Each sub-time period satisfies one or more of the following conditions: The time interval between any two adjacent data frames in the sub-time period is less than the interval threshold; The vehicles corresponding to any two adjacent data frames in the sub-time period are on the same road.

14. An energy consumption determination device, characterized in that: The device comprises: a determination unit and a processing unit; The determining unit is used to determine the battery net energy consumption corresponding to each of the multiple sub-time periods included in the target time period according to the driving data of the vehicle in the target time period; the battery net energy consumption is determined based on the energy consumed by the battery of the vehicle during the discharge process and the energy recovered by the energy recovery system; The processing unit is used to correct the battery net energy consumption corresponding to each sub-time period according to the battery net energy consumption and battery SOC changes corresponding to the multiple sub-time periods.

15. An electronic device, characterized in that: including memory and processor; The memory is coupled to the processor; The memory is used to store computer program code, wherein the computer program code includes computer instructions; When the processor executes the computer instructions, the electronic device performs the energy consumption determination method as described in any one of claims 1-13.

16. A computer-readable storage medium, characterized in that: When the computer-executable instructions stored in the computer-readable storage medium are executed by a processor of a processing device, the processing device can execute the energy consumption determination method according to any one of claims 1 to 13.

17. A computer program product, characterized in that The computer program product comprises the computer program, and the computer program is suitable for being loaded by a processor and executing the energy consumption determination method according to any one of claims 1 to 13.

Images